Social Desirability

Social desirability is the tendency of some respondents to report an answer in a way they deem to be more socially acceptable than would be their “true” answer. They do this to project a favorable image of themselves and to avoid receiving negative evaluations. The outcome of the strategy is overreporting of socially desirable behaviors or attitudes and underreporting of socially undesirable behaviors or attitudes. Social desirability is classified as one of the respondent-related sources of error (bias).

Social desirability bias intervenes in the last stage of the response process when the response is communicated to the researcher. In this step, a more or less deliberate editing of the response shifts the answer in the direction the respondent feels is more socially acceptable. Since the beginning of survey research, there have been many examples of socially desirable answers: for example, overreporting of having a library card, having voted, and attending church and underreporting of bankruptcy, drunken driving, illegal drug use, and negative racial attitudes.

The concept of social desirability has four nested characteristics: (1) The highest layer is a cultural characteristic, followed by (2) a personality characteristic, (3) mode of data collection, and (4) an item characteristic. The cultural characteristic is determined by the [Page 826]norms of that particular group or culture. For example, social desirability differs in conformist and individualist societies. Members of individualist societies tend to reveal more information about themselves to out-group representatives (the interviewer/researcher) than members of collectivist societies where the distinction between in-group and out-group is sharper. Within a society, specifie cultural groups differ in level of social desirability. For example, studies conducted in the United States have shown higher scores of social desirability for minority groups when compared to majority groups.

The second characteristic is tied to a personality trait. Researchers describe it as the need to conform to social standards and ultimately as a response style. Some scales have been developed to measure the tendency of respondents to portray themselves in a favorable light, for example, the Marlowe-Crowne scale, the Edwards Social Desirability scale, and the Eysenck Lie scale.

The third characteristic is at the mode of data collection level. Social desirability has been found to interact with some attributes of the interviewer and the respondent, such as race/ethnicity, gender, social class, and age. One of the most consistent findings in the literature is that self-administrated methods of data collection, such as mail surveys and Internet surveys, decrease the prevalence of social desirability bias. The general explanation is that the absence of the interviewer reduces the fear of receiving a negative evaluation, and responses are, therefore, more accurate. The item characteristic is the question wording. For items that have shown social desirability bias or that are expected to show it, some question wording techniques successfully reduce it. Methods include loading the question with reasonable excuses, using forgiving words, and assuming that respondents have engaged in the behavior instead of asking if they have. Another strategy is the randomized response method.

From a practical point of view, the researcher should be aware of potential social desirability effects—especially in cross-cultural research. Although the researcher has no control over the cultural and personal characteristics, question wording and mode of data collection can be used to decrease potentially socially desirable responses. Particular care should be taken when mixing modes of data collection.

...